Face Transfer with Generative Adversarial Network
|
|
- Shanon Chase
- 6 years ago
- Views:
Transcription
1 Face Transfer with Generative Adversarial Network Runze Xu, Zhiming Zhou, Weinan Zhang, Yong Yu Shanghai Jiao Tong University We explore the impact of discriminators with different receptive field sizes on the quality of generated images. We propose an architecture of two discriminators with differarxiv: v1 [cs.cv] 17 Oct 2017 Abstract Face transfer animates the facial performances of the character in the target video by a source actor. Traditional methods are typically based on face modeling. We propose an endto-end face transfer method based on Generative Adversarial Network. Specifically, we leverage CycleGAN to generate the face image of the target character with the corresponding head pose and facial expression of the source. In order to improve the quality of generated videos, we adopt Patch- GAN and explore the effect of different receptive field sizes on generated images. Introduction Face transfer is a method for mapping face performances of one individual to facial animations of another one. It uses facial expressions and head poses from the video of a source actor to generate a video of a target character. A variety of methods have been developed for face transfer and have achieved impressive results. Previous work typically models the face of source and target, and then transfers the corresponding features from the source to the target, and finally re-renders the target face and blends to the original target image to achieve face transfer (Vlasic et al. 2005; Shi et al. 2014; Thies et al. 2016). A data driven approach is proposed by (Li et al. 2012). They retrieved frames from a database based on a similarity metric and used optical flow as appearance and velocity measure and then searched for the k-nearest neighbors based on time stamps and flow distance. Different from the methods mentioned above which divide the task into several steps, and explicitly model the facial attributes, in this paper, we use deep neural network to develop an end-to-end approach (LeCun, Bengio, and Hinton 2015). Our work takes a talking video of a source actor as input. For every frame in the video, a face image of target character with corresponding facial expression and head pose is generated. By combining every generated frame, a corresponding video of the target character is generated. Face transfer is a special case of image-to-image translation tasks (Isola et al. 2016; Zhu et al. 2017). The characteristic of the input video is the appearance of the character Copyright c 2018, Association for the Advancement of Artificial Intelligence ( All rights reserved. in the video, while the identity of each frame is the character s facial expression and head pose. Our method is to use Generative Adversarial Network (GAN) (Goodfellow et al. 2014) to learn to transform the characteristic while preserving the identity. There are two key factors for this task. First, a source face image should be mapped to a target face image with the corresponding facial expression and head pose. Second, the image should be of high quality, i.e., looks natural and indistinguishable to human. In this paper, to generate images with matching facial expression and head pose, we use CycleGAN (Zhu et al. 2017) to transfer the identity between two image sets. CycleGAN is proposed to capture the special characteristics of one image collection and translate the characteristics into the other image collection in the absence of any paired training samples. CycleGAN learns a one-to-one mapping, which ensures each input face image can be mapped to a target image with a corresponding facial expression and head pose (Kim et al. 2017a). GAN is originally proposed to map the inputs to a real data distribution. A discriminator that models the whole images requires the generated images to be close to real images, which may restrict the creativity of the generator. (Isola et al. 2016) proposed that PatchGAN is an effective architecture in image-to-image translation tasks. Instead of a discriminator that performs a judge from the whole image. PatchGAN discriminator has a receptive field smaller than the whole image. It only models images from patch level and explicitly requires every image patch to be real. In that case, the generated image, composed by realistic image patches, can be more diverse, which enhances the generator s creativity. We study the impact of different receptive field sizes on the generators and use a model with a pair of discriminators with a big and small receptive fields respectively to capture both global coherence and local patterns. To sum up, our contributions are as follows. To the best of our knowledge, our work is the first that applies Generative Adversarial Network to perform endto-end face transfer which we formalize as an image-toimage translation problem.
2 ent receptive field sizes. This enables the generator to create images with a head pose that does not occur in the real image set. The demo video is provided at goo.gl/rbbr9y. Related Work Face Transfer (Vlasic et al. 2005) performed face transfer based on a multi-linear model of 3D face meshes that separably parameterizes the space of geometric variations due to different facial attributes. The authors tracked a face template and re-rendered it under different expression parameters. (Dale et al. 2011) tracked the facial performance in both videos. The authors warped the source to the target face and re-timed the source to match the target performance using the corresponding 3D geometry. (Garrido et al. 2014) proposed a reenactment pipeline conceived as part image retrieval and part face transfer. (Li et al. 2012) took advantage of an existing facial performance database of the target person. They used a query image to retrieve frames from a database based on similarity metrics. (Thies et al. 2016) investigated face trackers and expression modeling to transfer facial expressions and achieved real-time face transfer. Compared with above works, our approach uses generative adversarial network to achieve an end-to-end face transfer between two given characters without any supervision. We directly generate the target frames with the input frames of the source character. Image-to-Image Translation (Isola et al. 2016) pointed out that many problems in image processing, computer graphics, and computer vision can be formulated as an image-to-image translation task. For example, label to scene, aerial to map, day to night, edges to photo and also grayscale to color. Some problems in face synthesizing can also be regarded as image-to-image translation tasks. To be specific, changing attributes of face images, such as gender, hair style (Kim et al. 2017b), age, expression, beard and glasses (Shen and Liu 2016). In this paper, we also formulate face transfer as an image-to-image translation task. Generative Adversarial Networks Generative Adversarial Networks (GAN) (Goodfellow et al. 2014) has attained much attention in unsupervised learning during the recent 3 years. Conditional GAN, as a variant of GAN, is widely used in various computer vision scenarios. In some imageto-image translation tasks, the inputs are images rather than noises. (Zhu et al. 2017; Kim et al. 2017b; Yi et al. 2017) investigated similar cycle architecture and named this architecture as CycleGAN, DiscoGAN, DualGAN respectively. In this paper, we refer to this architecture as CycleGAN. Compared with traditional GAN which has only a generator G mapping domain X to domain Y and a discriminator on domain Y. CycleGAN adds another generator F mapping domain Y to domain X and a discriminator on domain X. The two GANs form a cycle transformation, and cycle consistency loss is introduced to urge the cycle transformation to be identical. Such a cycle architecture can be applied to unpaired data (Zhu et al. 2017). We leverage cycle architecture to transfer the facial performance from the source character to the target character, with two unpaired videos, one for each character. (Isola et al. 2016) proposed PatchGAN as an effective architecture in image-to-image translation tasks. It restricts the discriminator to image patches in order to model highfrequency structures. And the authors showed that Patch- GAN is effective on a wider range of problems. A similar PatchGAN architecture was previously proposed in (Li and Wand 2016), for the purpose of capturing local style statistics. Such a discriminator models the image as a Markov random field (Li and Wand 2016). PatchGAN is also used in further studies such as unpaired settings (Zhu et al. 2017) and dual learning (Yi et al. 2017). In this paper, we explore the effect of PatchGAN discriminators with different receptive field sizes. GAN with Multi-Discriminators Despite the impressive results achieved by GANs. GANs are reputably difficult to train. It is hard to balance the generator and the discriminator, and it easily gets mode-collapse. (Durugkar, Gemp, and Mahadevan 2016) extended GANs to multiple discriminators. For a generator G, N discriminators of the same structure with random initialization are utilized as teachers for the generator. They suggested that GANs with multiple discriminators can better approximate the optimal discriminator, and are more stable on providing reliable feedback for the generator. In this paper, we experiment with the framework of two discriminators against one generator. Note that our discriminators are PatchGAN discriminators. We explore the case of two discriminators with the same structure and the case of two discriminators with different receptive field sizes. For the latter case, one discriminator has a large receptive field and another has a small receptive field. Preliminaries In this section, we discuss some preliminaries of our models, including GANs and CycleGAN framework. A Generative Adversarial Network is a generative model that consists of two neural networks. A generator G learns to map random noise vector z to real data distribution: G : z x. A discriminator D tries to distinguish real data from generated samples. They are iteratively trained to play a twoplayer min-max game. In image-to-image translation tasks, the generator takes in images as input instead of noise and maps images from X to target domain Y : G : X Y. We follow the choice of (Zhu et al. 2017) which adopts least square loss instead of the negative log likelihood. The adversarial loss is defined as L GAN (G, D Y ) =E y Pdata (y)[(d Y (y) a) 2 ] + E x Pdata (x)[d Y (G(x)) 2 ]. (1) CycleGAN, in addition to traditional GANs, adopts two pairs of generator and discriminator. A generator G that maps X to Y with a discriminator on domain Y and a generator F that maps Y to X with a discriminator on domain X. The two GANs are trained simultaneously. Each image
3 x in domain X transformed by G to domain Y is then transformed back to domain X by F : x G(x) F (G(x)). CycleGAN introduces a cycle consistency loss which enforces x and G(F (x)) to be consistent. Such a cycle architecture can thus be applied to unpaired data. The loss function of cycle consistency loss is defined as L cyc (G, F ) =E x Pdata (x)[ F (G(x)) x ] + E y Pdata (y)[ G(F (y)) y ], (2) where we follow (Zhu et al. 2017; Yi et al. 2017) to adopt L1 norm to measure the cycle consistency loss 1. The cycle consistency loss consists of two parts. They are conditioned on both G and F. When minimizing E x Pdata (x)[ F (G(x)) x) ], G is optimized to transform a real image x to a generated sample that contains sufficient information to be transformed back to x. When minimizing E y Pdata (y)[ G(F (y)) y ], G is optimized to adapt a fake sample F (y) back to a real image y. Our Method We empirically find that the original definition of the cycle consistency loss makes the generators prone to generate artifacts meaningless to human. Thus we make a small modification: both generators only take real images as input and will not be trained on fake images during training: L cyc (G) = E x Pdata (x)[ F (G(x)) x) ] L cyc (F ) = E y Pdata (y)[ G(F (y)) y) ] (3) Such a modification helps reduce some artifacts. Original CycleGAN fixes the weight of adversarial losses to 1.0 and the two parts of cycle consistency share a weight parameter. We find different datasets are different in susceptibility to mode collapse. And the ratio of cycle loss and adversarial loss should be different for different datasets. Therefore, we introduce weights for different cycle passes as hyperparameters, and define the full objective function as L(G, F, D X, D Y ) =αl GAN (G, D Y ) + βl GAN (F, D X ) + λl cyc (G) + λl cyc (F ), (4) where α, β and λ are the hyperparameters. PatchGAN Discriminators For discriminators, we employ Markovian PatchGAN discriminator (Isola et al. 2016; Li and Wand 2016), which models images only at patch level rather than the whole image. It assumes independence between pixels separated by more than a patch diameter. The discriminator is run convolutionally across the image and the losses of all image patches are averaged to provide the final loss of the discriminator. PatchGAN discriminator is effective in capturing local high-frequency features but less effective in modeling global structure. The choice of receptive field size is a staggering problem. In some image-to-image translation tasks, such as edge to 1 We also experimented with L2 norm, but found that L1 norm is more robust to mode collapse. photo, labels to street scene and grayscale to color (Isola et al. 2016), the generator changes the local style while preserving spatial information. The shape of the objects in the picture usually remains unchanged. The receptive field of discriminators in these tasks could be more arbitrary than that of our case. For example, in (Isola et al. 2016), they experimented 1 1, 16 16, 70 70, on images and got visually similar results with ImageGAN and PatchGAN. In our face transfer task, we find the receptive field size strongly affects the quality of generated faces. With a small receptive field, only generated image patches are required to be realistic, which results in more diverse generated images and enhances the generator s creativity, especially on a dataset with limited samples. While, for the fact that we are modeling an image of a entire face, we need a discriminator with a receptive field close to image size. If the receptive field is too small, it will result in unreasonable deformation of generated faces. Multiple Discriminators A discriminator with limited capacity may fail to generate realistic images. However, modification on the discriminator s structure is often along with a difficulty in training GANs. When the discriminator reaches a far superior situation to the generator, the generator may stop making progress (Durugkar, Gemp, and Mahadevan 2016; Arjovsky and Bottou 2017; Neyshabur, Bhojanapalli, and Chakrabarti 2017). When the distribution of generated samples has little overlap with real image distribution, the generator cannot receive efficient gradients from the discriminator to improve its performance, which is referred as the gradient vanishing problem in GAN (Arjovsky, Chintala, and Bottou 2017). We introduce the scheme of training two discriminators against one generator as a more stable way to improve the capacity of discriminators, as similar to (Durugkar, Gemp, and Mahadevan 2016). To be specific, the multidiscriminator architecture can better approximate the optimal discriminator, and, if one of the discriminators is trained to be far superior over the generator, the generator can still receive instructive gradients from the other discriminator. Choice of Receptive Fields In the two-discriminator setting, we conduct experiments with three different pairs of receptive field sizes. To ensure justice, all models have two discriminators against one generator. The performance of these models will be shown and analyzed in Experiments Section. For the first case, both discriminators are with receptive field sizes of the size The two discriminators share the same structure but are randomly instantiated. We simply average their losses as the final adversarial loss. Such a receptive field is close to image size. It models real images from a global view. Therefore, if a generated face image exhibits a pose that never occurs in the real image set, the discriminator will give a low score and prevent the generator from generating such images, which restricts the creativity of the generator.
4 For the second case, we use two discriminators with receptive fields. Because the discriminator only models local patterns of real images and it does not require the whole generated image to be similar to real images. The generator has little restriction on the global structure, which enables the generator to transform images with head poses that never occur in the target domain into a much better sample than the case mentioned above. In other words, it enhances the generator s creativity. However, discriminators with small receptive fields cannot model global features, which results in global inconformities such as excessive deformation of generated eyes and face. For the third case, one discriminator has a receptive field, while the other has a receptive field. It is a trade-off between the two cases mentioned above that models global and local structure simultaneously. We add parameters to tune weight of the two adversarial losses. We hope this model can take both global features and local features into consideration. While the discriminator improves the generator s creativity, the discriminator can help eliminate those abrupt deformation caused by the absence of global inspection. For the mapping function G : X Y, The formulation of the final adversarial loss is defined as L GAN (G, D Y1, D Y2 ) =γ L GAN (G, D Y1 ) + (1 γ) L GAN (G, D Y2 ), (5) where γ is the hyperparameter to maintain the ratio between the adversarial losses of the two discriminators. Note that D Y1 and D Y2 are two discriminator instances. In the first two cases, γ is set as 0.5 as the balance of the two factors are not sensitive to the final results. In the third case, γ needs to be carefully tuned as it is sensitive to the performance. Datasets Experiments We conduct experiments on three clips: Barack Obama in weekly address Joe Biden in weekly address Li Xiuping in CCTV News We manually crop the 3 videos and extract the frames of the cropped video. All of these video clips are mainly a character talking to the camera. We choose these videos based on the following reasons. Because we aim at transferring the facial performance, each video includes the facial part of a acting character. In our video clips, body parts usually do not appear in the cropped video and the shooting angles are fixed, otherwise, irrespective body movements and the changing of shooting angle may also be considered as important identities by the generator. The images are scaled to Most input images with common facial expression and head pose are transformed into realistic samples in the target domain. Example results are shown in Figure 1. Performance of Different Receptive Fields In this section, we compare the performance of three models. They all have two discriminators trained against one generator. The first model has two PatchGAN discriminators with receptive field, represented by model. The second has two discriminators with receptive field, represented by model.the third has a discriminator with receptive field and a discriminator with receptive field, represented by model. To illustrate the difference between the three models, we compare their performance on the task Joe Biden Li Xiuping. This is the most difficult task in the three datasets for two reasons. First, Joe Biden is an English speaker while Li Xiuping is a Chinese speaker. There is no counterpart for some mouth shapes in Joe Biden s video. Second, Joe Biden moves his head arbitrarily in his video while Li Xiuping moves in a small range. We pick the representative frames that illustrate the advantages and disadvantages of the three models discriminator models global structure of images, which restricts the generator s creativity. It makes the generator generates noisy and distorted face images if the source image exhibits a head pose unseen in target image set discriminator allows the generator to generate uncommon head pose but cannot ensure global features. The model is a trade-off between global and local features. By tuning the weight of two discriminators adversarial losses, we achieved high-quality results. Creativity on Unseen Head Poses In the video of Joe Biden, he sometimes raises his head, sometimes tilts his head drastically, while Li Xiuping never does so in her video. So there is no image that can be considered as a direct reference. Joe Biden in the source frames raises his head, as shown in Figure 3. The model generates distorted faces, for the discriminator models the whole images and it considers the unseen head pose as a fake sample, which hinders the generator from creating unseen head poses. The other two models generate meaningful faces, although there are some artifacts on the neck. The results of model and model are similar. In another video fragment, Figure 2, Joe Biden tilts his head drastically model generates a face image with noise everywhere model generates a clear face, but causes unpleasant deformation of the generated face. This is because the discriminator cannot model the whole face. It only inspects generated images from a local perspective. Without the restriction on global features, it cannot penalize the obvious global deformation discriminator models both global and local structures, which leads to much better results. Limitation In this section, we discuss the limitation of our face transfer method. We show the performance of our three models on generating unseen expressions in Figure 4. We cut a fragment of video in which Joe Biden grins broadly to
5 Figure 1: Example results: the odd rows are real source images and the even rows are generated target images. pronounce any. It is hard to find a similar mouth shape in Chinese, let alone a short video of Li Xiuping. Without a reference, it is hard to generate a sharp and realistic mouth with our approach model generates a mouth that resembles the source image in the overall shape but cannot create the details of teeth. CycleGAN encourages the generator to map a source image to a target image with identical facial expression and head pose. However, when the source and target video do not match in the diversity of head pose and facial expressions, it is hard to learn a perfect one-to-one mapping, which results in noisy and distorted results as shown in Figure 2, Figure 3 and Figure 4. To address this issue we adopt our two-discriminator architecture to create some unseen poses. Conclusions In this paper, we leverage CycleGAN and PatchGAN to achieve an end-to-end face transfer. CycleGAN learns a oneto-one mapping, which ensures each source face image to be mapped to a target image with a corresponding facial expression and head pose. Practically, with limited training samples, it is difficult to well generate the corresponding target face image with unseen facial expression or head pose in the target dataset. To improve the generalization ability of the generator, we propose to adopt a discriminator with a small receptive field to alleviate the restriction on the generator and a discriminator with a big receptive field to ensure global coherence. This two-discriminator architecture achieves the best result in our experiments. For the future work, loss re-weighting on image patches could help improve generated image quality. And an investigation on the impact of receptive field size on other imageto-image translation tasks is also interesting. References [Arjovsky and Bottou 2017] Arjovsky, M., and Bottou, L Towards principled methods for training generative adversarial networks. arxiv preprint arxiv: [Arjovsky, Chintala, and Bottou 2017] Arjovsky, M.; Chintala, S.; and Bottou, L Wasserstein gan. ICML. [Dale et al. 2011] Dale, K.; Sunkavalli, K.; Johnson, M. K.; Vlasic, D.; Matusik, W.; and Pfister, H Video face replacement. ACM Transactions on Graphics (TOG) 30(6):130. [Durugkar, Gemp, and Mahadevan 2016] Durugkar, I.; Gemp, I.; and Mahadevan, S Generative multiadversarial networks. arxiv preprint arxiv: [Garrido et al. 2014] Garrido, P.; Valgaerts, L.; Rehmsen, O.; Thormahlen, T.; Perez, P.; and Theobalt, C Automatic face reenactment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, [Goodfellow et al. 2014] Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville,
6 Source Source Figure 2: The first column are three frames in succession model fails to generate clear images model generates much better images but results in abrupt deformation model alleviates the deformation and achieves images close to real images. Figure 3: The first column are three source frames in succession. The other columns are results of different models model generates distorted faces and model generate similar result. Source Figure 4: The performance of three models on generating an unseen mouth. A.; and Bengio, Y Generative adversarial nets. In Advances in neural information processing systems, [Isola et al. 2016] Isola, P.; Zhu, J.-Y.; Zhou, T.; and Efros, A. A Image-to-image translation with conditional adversarial networks. arxiv preprint arxiv: [Kim et al. 2017a] Kim, T.; Cha, M.; Kim, H.; Lee, J.; and Kim, J. 2017a. Learning to discover cross-domain relations with generative adversarial networks. arxiv preprint arxiv: [Kim et al. 2017b] Kim, T.; Kim, B.; Cha, M.; and Kim, J. 2017b. Unsupervised visual attribute transfer with reconfigurable generative adversarial networks. arxiv preprint arxiv: [LeCun, Bengio, and Hinton 2015] LeCun, Y.; Bengio, Y.; and Hinton, G Deep learning. Nature 521(7553): [Li and Wand 2016] Li, C., and Wand, M Precomputed real-time texture synthesis with markovian generative adversarial networks. In European Conference on Computer Vision, Springer. [Li et al. 2012] Li, K.; Xu, F.; Wang, J.; Dai, Q.; and Liu, Y A data-driven approach for facial expression synthesis in video. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, IEEE. [Lin et al. 2017] Lin, T.-Y.; Goyal, P.; Girshick, R.; He, K.; and Dollár, P Focal loss for dense object detection. arxiv preprint arxiv: [Neyshabur, Bhojanapalli, and Chakrabarti 2017] Neyshabur, B.; Bhojanapalli, S.; and Chakrabarti, A Stabilizing gan training with multiple random projections. arxiv preprint arxiv: [Shen and Liu 2016] Shen, W., and Liu, R Learning residual images for face attribute manipulation. arxiv preprint arxiv: [Shi et al. 2014] Shi, F.; Wu, H.-T.; Tong, X.; and Chai, J Automatic acquisition of high-fidelity facial performances using monocular videos. ACM Transactions on Graphics (TOG) 33(6):222. [Thies et al. 2016] Thies, J.; Zollhofer, M.; Stamminger, M.; Theobalt, C.; and Nießner, M Face2face: Real-time face capture and reenactment of rgb videos. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, [Vlasic et al. 2005] Vlasic, D.; Brand, M.; Pfister, H.; and Popović, J Face transfer with multilinear models. In ACM transactions on graphics (TOG), volume 24, ACM. [Yi et al. 2017] Yi, Z.; Zhang, H.; Gong, P. T.; et al
7 Dualgan: Unsupervised dual learning for image-to-image translation. arxiv preprint arxiv: [Zhu et al. 2017] Zhu, J.-Y.; Park, T.; Isola, P.; and Efros, A. A Unpaired image-to-image translation using cycle-consistent adversarial networks. arxiv preprint arxiv:
An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks
An Empirical Study of Generative Adversarial Networks for Computer Vision Tasks Report for Undergraduate Project - CS396A Vinayak Tantia (Roll No: 14805) Guide: Prof Gaurav Sharma CSE, IIT Kanpur, India
More informationarxiv: v1 [cs.cv] 5 Jul 2017
AlignGAN: Learning to Align Cross- Images with Conditional Generative Adversarial Networks Xudong Mao Department of Computer Science City University of Hong Kong xudonmao@gmail.com Qing Li Department of
More informationProgress on Generative Adversarial Networks
Progress on Generative Adversarial Networks Wangmeng Zuo Vision Perception and Cognition Centre Harbin Institute of Technology Content Image generation: problem formulation Three issues about GAN Discriminate
More informationDeep Fakes using Generative Adversarial Networks (GAN)
Deep Fakes using Generative Adversarial Networks (GAN) Tianxiang Shen UCSD La Jolla, USA tis038@eng.ucsd.edu Ruixian Liu UCSD La Jolla, USA rul188@eng.ucsd.edu Ju Bai UCSD La Jolla, USA jub010@eng.ucsd.edu
More informationTwo Routes for Image to Image Translation: Rule based vs. Learning based. Minglun Gong, Memorial Univ. Collaboration with Mr.
Two Routes for Image to Image Translation: Rule based vs. Learning based Minglun Gong, Memorial Univ. Collaboration with Mr. Zili Yi Introduction A brief history of image processing Image to Image translation
More informationarxiv: v1 [cs.cv] 1 Nov 2018
Examining Performance of Sketch-to-Image Translation Models with Multiclass Automatically Generated Paired Training Data Dichao Hu College of Computing, Georgia Institute of Technology, 801 Atlantic Dr
More informationLearning to generate with adversarial networks
Learning to generate with adversarial networks Gilles Louppe June 27, 2016 Problem statement Assume training samples D = {x x p data, x X } ; We want a generative model p model that can draw new samples
More informationarxiv: v2 [cs.cv] 16 Dec 2017
CycleGAN, a Master of Steganography Casey Chu Stanford University caseychu@stanford.edu Andrey Zhmoginov Google Inc. azhmogin@google.com Mark Sandler Google Inc. sandler@google.com arxiv:1712.02950v2 [cs.cv]
More informationGAN Related Works. CVPR 2018 & Selective Works in ICML and NIPS. Zhifei Zhang
GAN Related Works CVPR 2018 & Selective Works in ICML and NIPS Zhifei Zhang Generative Adversarial Networks (GANs) 9/12/2018 2 Generative Adversarial Networks (GANs) Feedforward Backpropagation Real? z
More informationarxiv: v1 [cs.cv] 16 Jul 2017
enerative adversarial network based on resnet for conditional image restoration Paper: jc*-**-**-****: enerative Adversarial Network based on Resnet for Conditional Image Restoration Meng Wang, Huafeng
More informationMoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction
MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction Ayush Tewari Michael Zollhofer Hyeongwoo Kim Pablo Garrido Florian Bernard Patrick Perez Christian Theobalt
More informationarxiv: v1 [cs.cv] 7 Mar 2018
Accepted as a conference paper at the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2018 Inferencing Based on Unsupervised Learning of Disentangled
More informationComposable Unpaired Image to Image Translation
Composable Unpaired Image to Image Translation Laura Graesser New York University lhg256@nyu.edu Anant Gupta New York University ag4508@nyu.edu Abstract There has been remarkable recent work in unpaired
More informationLecture 3 GANs and Their Applications in Image Generation
Lecture 3 GANs and Their Applications in Image Generation Lin ZHANG, PhD School of Software Engineering Tongji University Fall 2017 Outline Introduction Theoretical Part Application Part Existing Implementations
More informationSupplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
Supplementary Material: Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos Kihyuk Sohn 1 Sifei Liu 2 Guangyu Zhong 3 Xiang Yu 1 Ming-Hsuan Yang 2 Manmohan Chandraker 1,4 1 NEC Labs
More informationarxiv: v1 [cs.cv] 6 Sep 2018
arxiv:1809.01890v1 [cs.cv] 6 Sep 2018 Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks Koichi Hamada, Kentaro Tachibana, Tianqi Li, Hiroto
More informationarxiv: v1 [cs.cv] 1 May 2018
Conditional Image-to-Image Translation Jianxin Lin 1 Yingce Xia 1 Tao Qin 2 Zhibo Chen 1 Tie-Yan Liu 2 1 University of Science and Technology of China 2 Microsoft Research Asia linjx@mail.ustc.edu.cn {taoqin,
More informationarxiv: v1 [cs.ne] 11 Jun 2018
Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks arxiv:1806.03796v1 [cs.ne] 11 Jun 2018 Yash Upadhyay University of Minnesota, Twin Cities Minneapolis, MN, 55414
More informationControllable Generative Adversarial Network
Controllable Generative Adversarial Network arxiv:1708.00598v2 [cs.lg] 12 Sep 2017 Minhyeok Lee 1 and Junhee Seok 1 1 School of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul,
More informationDeep Learning for Visual Manipulation and Synthesis
Deep Learning for Visual Manipulation and Synthesis Jun-Yan Zhu 朱俊彦 UC Berkeley 2017/01/11 @ VALSE What is visual manipulation? Image Editing Program input photo User Input result Desired output: stay
More informationVisual Recommender System with Adversarial Generator-Encoder Networks
Visual Recommender System with Adversarial Generator-Encoder Networks Bowen Yao Stanford University 450 Serra Mall, Stanford, CA 94305 boweny@stanford.edu Yilin Chen Stanford University 450 Serra Mall
More informationDCGANs for image super-resolution, denoising and debluring
DCGANs for image super-resolution, denoising and debluring Qiaojing Yan Stanford University Electrical Engineering qiaojing@stanford.edu Wei Wang Stanford University Electrical Engineering wwang23@stanford.edu
More informationSynthesizing Realistic Facial Expressions from Photographs
Synthesizing Realistic Facial Expressions from Photographs 1998 F. Pighin, J Hecker, D. Lischinskiy, R. Szeliskiz and D. H. Salesin University of Washington, The Hebrew University Microsoft Research 1
More informationarxiv: v1 [eess.sp] 23 Oct 2018
Reproducing AmbientGAN: Generative models from lossy measurements arxiv:1810.10108v1 [eess.sp] 23 Oct 2018 Mehdi Ahmadi Polytechnique Montreal mehdi.ahmadi@polymtl.ca Mostafa Abdelnaim University de Montreal
More informationCost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling
[DOI: 10.2197/ipsjtcva.7.99] Express Paper Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling Takayoshi Yamashita 1,a) Takaya Nakamura 1 Hiroshi Fukui 1,b) Yuji
More informationDOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION
DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION Yen-Cheng Liu 1, Wei-Chen Chiu 2, Sheng-De Wang 1, and Yu-Chiang Frank Wang 1 1 Graduate Institute of Electrical Engineering,
More informationUnsupervised Learning
Deep Learning for Graphics Unsupervised Learning Niloy Mitra Iasonas Kokkinos Paul Guerrero Vladimir Kim Kostas Rematas Tobias Ritschel UCL UCL/Facebook UCL Adobe Research U Washington UCL Timetable Niloy
More informationGenerative Models II. Phillip Isola, MIT, OpenAI DLSS 7/27/18
Generative Models II Phillip Isola, MIT, OpenAI DLSS 7/27/18 What s a generative model? For this talk: models that output high-dimensional data (Or, anything involving a GAN, VAE, PixelCNN, etc) Useful
More informationDe-mark GAN: Removing Dense Watermark With Generative Adversarial Network
De-mark GAN: Removing Dense Watermark With Generative Adversarial Network Jinlin Wu, Hailin Shi, Shu Zhang, Zhen Lei, Yang Yang, Stan Z. Li Center for Biometrics and Security Research & National Laboratory
More informationSYNTHESIS OF IMAGES BY TWO-STAGE GENERATIVE ADVERSARIAL NETWORKS. Qiang Huang, Philip J.B. Jackson, Mark D. Plumbley, Wenwu Wang
SYNTHESIS OF IMAGES BY TWO-STAGE GENERATIVE ADVERSARIAL NETWORKS Qiang Huang, Philip J.B. Jackson, Mark D. Plumbley, Wenwu Wang Centre for Vision, Speech and Signal Processing University of Surrey, Guildford,
More informationDOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION
2017 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 25 28, 2017, TOKYO, JAPAN DOMAIN-ADAPTIVE GENERATIVE ADVERSARIAL NETWORKS FOR SKETCH-TO-PHOTO INVERSION Yen-Cheng Liu 1,
More informationGENERATIVE ADVERSARIAL NETWORK-BASED VIR-
GENERATIVE ADVERSARIAL NETWORK-BASED VIR- TUAL TRY-ON WITH CLOTHING REGION Shizuma Kubo, Yusuke Iwasawa, and Yutaka Matsuo The University of Tokyo Bunkyo-ku, Japan {kubo, iwasawa, matsuo}@weblab.t.u-tokyo.ac.jp
More informationAttribute-Guided Face Generation Using Conditional CycleGAN
Attribute-Guided Face Generation Using Conditional CycleGAN Yongyi Lu 1[0000 0003 1398 9965], Yu-Wing Tai 2[0000 0002 3148 0380], and Chi-Keung Tang 1[0000 0001 6495 3685] 1 The Hong Kong University of
More informationLearning Social Graph Topologies using Generative Adversarial Neural Networks
Learning Social Graph Topologies using Generative Adversarial Neural Networks Sahar Tavakoli 1, Alireza Hajibagheri 1, and Gita Sukthankar 1 1 University of Central Florida, Orlando, Florida sahar@knights.ucf.edu,alireza@eecs.ucf.edu,gitars@eecs.ucf.edu
More informationarxiv: v1 [stat.ml] 14 Sep 2017
The Conditional Analogy GAN: Swapping Fashion Articles on People Images Nikolay Jetchev Zalando Research nikolay.jetchev@zalando.de Urs Bergmann Zalando Research urs.bergmann@zalando.de arxiv:1709.04695v1
More informationarxiv: v1 [cs.cv] 1 Dec 2017
Multi-Content GAN for Few-Shot Font Style Transfer Samaneh Azadi 1, Matthew Fisher 2, Vladimir Kim 2, Zhaowen Wang 2, Eli Shechtman 2, Trevor Darrell 1 1 UC Berkeley, 2 Adobe Research {sazadi,trevor}@eecs.berkeley.edu
More informationarxiv: v2 [cs.cv] 14 Jul 2018
Constrained Neural Style Transfer for Decorated Logo Generation arxiv:1803.00686v2 [cs.cv] 14 Jul 2018 Gantugs Atarsaikhan, Brian Kenji Iwana, Seiichi Uchida Graduate School of Information Science and
More informationarxiv: v3 [cs.cv] 9 Aug 2017
DualGAN: Unsupervised Dual Learning for Image-to-Image Translation Zili Yi 1,2, Hao Zhang 2, Ping Tan 2, and Minglun Gong 1 1 Memorial University of Newfoundland, Canada 2 Simon Fraser University, Canada
More informationIntroduction to Generative Adversarial Networks
Introduction to Generative Adversarial Networks Luke de Oliveira Vai Technologies Lawrence Berkeley National Laboratory @lukede0 @lukedeo lukedeo@vaitech.io https://ldo.io 1 Outline Why Generative Modeling?
More informationWhat was Monet seeing while painting? Translating artworks to photo-realistic images M. Tomei, L. Baraldi, M. Cornia, R. Cucchiara
What was Monet seeing while painting? Translating artworks to photo-realistic images M. Tomei, L. Baraldi, M. Cornia, R. Cucchiara COMPUTER VISION IN THE ARTISTIC DOMAIN The effectiveness of Computer Vision
More informationSeismic data reconstruction with Generative Adversarial Networks
Seismic data reconstruction with Generative Adversarial Networks Ali Siahkoohi 1, Rajiv Kumar 1,2 and Felix J. Herrmann 2 1 Seismic Laboratory for Imaging and Modeling (SLIM), The University of British
More informationRecovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Xintao Wang Ke Yu Chao Dong Chen Change Loy Problem enlarge 4 times Low-resolution image High-resolution image Previous
More informationPaired 3D Model Generation with Conditional Generative Adversarial Networks
Accepted to 3D Reconstruction in the Wild Workshop European Conference on Computer Vision (ECCV) 2018 Paired 3D Model Generation with Conditional Generative Adversarial Networks Cihan Öngün Alptekin Temizel
More informationTHERMAL TEXTURE GENERATION AND 3D MODEL RECONSTRUCTION USING SFM AND GAN
THERMAL TEXTURE GENERATION AND 3D MODEL RECONSTRUCTION USING SFM AND GAN V. V. Kniaz a,b, V. A. Mizginov a a State Res. Institute of Aviation Systems (GosNIIAS), 125319, 7, Victorenko str., Moscow, Russia
More informationInstance Map based Image Synthesis with a Denoising Generative Adversarial Network
Instance Map based Image Synthesis with a Denoising Generative Adversarial Network Ziqiang Zheng, Chao Wang, Zhibin Yu*, Haiyong Zheng, Bing Zheng College of Information Science and Engineering Ocean University
More informationarxiv: v1 [cs.cv] 3 Apr 2019
Unpaired Thermal to Visible Spectrum Transfer using Adversarial Training Adam Nyberg 1[0000 0001 8764 8499], Abdelrahman Eldesokey 1[0000 0003 3292 7153], David Bergström 2[0000 0003 2414 4482], and David
More informationShow, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks
Show, Discriminate, and Tell: A Discriminatory Image Captioning Model with Deep Neural Networks Zelun Luo Department of Computer Science Stanford University zelunluo@stanford.edu Te-Lin Wu Department of
More informationarxiv: v1 [cs.cv] 3 Aug 2017
Deep MR to CT Synthesis using Unpaired Data Jelmer M. Wolterink 1, Anna M. Dinkla 2, Mark H.F. Savenije 2, Peter R. Seevinck 1, Cornelis A.T. van den Berg 2, Ivana Išgum 1 1 Image Sciences Institute, University
More informationInverting The Generator Of A Generative Adversarial Network
1 Inverting The Generator Of A Generative Adversarial Network Antonia Creswell and Anil A Bharath, Imperial College London arxiv:1802.05701v1 [cs.cv] 15 Feb 2018 Abstract Generative adversarial networks
More informationAlternatives to Direct Supervision
CreativeAI: Deep Learning for Graphics Alternatives to Direct Supervision Niloy Mitra Iasonas Kokkinos Paul Guerrero Nils Thuerey Tobias Ritschel UCL UCL UCL TUM UCL Timetable Theory and Basics State of
More informationarxiv: v1 [cs.cv] 19 Nov 2018
Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention arxiv:1811.07483v1 [cs.cv] 19 Nov 2018 Abstract Honglun Zhang 1, Wenqing Chen 1, Jidong Tian 1, Yongkun
More informationarxiv: v1 [cs.cv] 8 May 2018
arxiv:1805.03189v1 [cs.cv] 8 May 2018 Learning image-to-image translation using paired and unpaired training samples Soumya Tripathy 1, Juho Kannala 2, and Esa Rahtu 1 1 Tampere University of Technology
More informationStarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation Yunjey Choi 1,2 Minje Choi 1,2 Munyoung Kim 2,3 Jung-Woo Ha 2 Sunghun Kim 2,4 Jaegul Choo 1,2 1 Korea University
More informationDeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material
DeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material Yi Li 1, Gu Wang 1, Xiangyang Ji 1, Yu Xiang 2, and Dieter Fox 2 1 Tsinghua University, BNRist 2 University of Washington
More informationPairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup
PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup Huiwen Chang Princeton University Jingwan Lu Adobe Research Fisher Yu UC Berkeley Abstract Adam Finkelstein Princeton University
More informationExemplar-Supported Generative Reproduction for Class Incremental Learning Supplementary Material
HE ET AL.: EXEMPLAR-SUPPORTED GENERATIVE REPRODUCTION 1 Exemplar-Supported Generative Reproduction for Class Incremental Learning Supplementary Material Chen He 1,2 chen.he@vipl.ict.ac.cn Ruiping Wang
More informationAdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation
AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation Introduction Supplementary material In the supplementary material, we present additional qualitative results of the proposed AdaDepth
More informationarxiv: v1 [cs.cg] 24 Aug 2018
High Quality Facial Surface and Texture Synthesis via Generative Adversarial Networks Ron Slossberg 1 *, Gil Shamai 2 *, and Ron Kimmel 1 arxiv:1808.08281v1 [cs.cg] 24 Aug 2018 1 Technion CS department,
More informationPedestrian and Part Position Detection using a Regression-based Multiple Task Deep Convolutional Neural Network
Pedestrian and Part Position Detection using a Regression-based Multiple Tas Deep Convolutional Neural Networ Taayoshi Yamashita Computer Science Department yamashita@cs.chubu.ac.jp Hiroshi Fuui Computer
More informationRealistic Dynamic Facial Textures from a Single Image using GANs
Realistic Dynamic Facial Textures from a Single Image using GANs Kyle Olszewski 1,3,4, Zimo Li 1, Chao Yang 1, Yi Zhou 1, Ronald Yu 1,3, Zeng Huang 1, Sitao Xiang 1, Shunsuke Saito 1,3, Pushmeet Kohli
More informationDual Learning of the Generator and Recognizer for Chinese Characters
2017 4th IAPR Asian Conference on Pattern Recognition Dual Learning of the Generator and Recognizer for Chinese Characters Yixing Zhu, Jun Du and Jianshu Zhang National Engineering Laboratory for Speech
More informationFace2Face Comparing faces with applications Patrick Pérez. Inria, Rennes 2 Oct. 2014
Face2Face Comparing faces with applications Patrick Pérez Inria, Rennes 2 Oct. 2014 Outline Metric learning for face comparison Expandable parts model and occlusions Face sets comparison Identity-based
More informationExploring Style Transfer: Extensions to Neural Style Transfer
Exploring Style Transfer: Extensions to Neural Style Transfer Noah Makow Stanford University nmakow@stanford.edu Pablo Hernandez Stanford University pabloh2@stanford.edu Abstract Recent work by Gatys et
More information(x,y) G(x,y) Generating a Fusion Image: One s Identity and Another s Shape
enerating a Fusion Image: One s Identity and Another s Shape Donggyu Joo Doyeon Kim Junmo Kim School of Electrical Engineering, KAIST, South Korea {jdg105, doyeon kim, junmo.kim}@kaist.ac.kr Abstract enerating
More informationarxiv: v1 [cs.cv] 29 Nov 2017
Photo-to-Caricature Translation on Faces in the Wild Ziqiang Zheng Haiyong Zheng Zhibin Yu Zhaorui Gu Bing Zheng Ocean University of China arxiv:1711.10735v1 [cs.cv] 29 Nov 2017 Abstract Recently, image-to-image
More informationECCV Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016
ECCV 2016 Presented by: Boris Ivanovic and Yolanda Wang CS 331B - November 16, 2016 Fundamental Question What is a good vector representation of an object? Something that can be easily predicted from 2D
More informationColorization Using ConvNet and GAN
Colorization Using ConvNet and GAN Qiwen Fu qiwenfu@stanford.edu Stanford Univeristy Wei-Ting Hsu hsuwt@stanford.edu Stanford University Mu-Heng Yang mhyang@stanford.edu Stanford University Abstract Colorization
More informationLab meeting (Paper review session) Stacked Generative Adversarial Networks
Lab meeting (Paper review session) Stacked Generative Adversarial Networks 2017. 02. 01. Saehoon Kim (Ph. D. candidate) Machine Learning Group Papers to be covered Stacked Generative Adversarial Networks
More informationChannel Locality Block: A Variant of Squeeze-and-Excitation
Channel Locality Block: A Variant of Squeeze-and-Excitation 1 st Huayu Li Northern Arizona University Flagstaff, United State Northern Arizona University hl459@nau.edu arxiv:1901.01493v1 [cs.lg] 6 Jan
More informationAttribute Augmented Convolutional Neural Network for Face Hallucination
Attribute Augmented Convolutional Neural Network for Face Hallucination Cheng-Han Lee 1 Kaipeng Zhang 1 Hu-Cheng Lee 1 Chia-Wen Cheng 2 Winston Hsu 1 1 National Taiwan University 2 The University of Texas
More informationS+U Learning through ANs - Pranjit Kalita
S+U Learning through ANs - Pranjit Kalita - (from paper) Learning from Simulated and Unsupervised Images through Adversarial Training - Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda
More informationSupplemental Document for Deep Photo Style Transfer
Supplemental Document for Deep Photo Style Transfer Fujun Luan Cornell University Sylvain Paris Adobe Eli Shechtman Adobe Kavita Bala Cornell University fujun@cs.cornell.edu sparis@adobe.com elishe@adobe.com
More informationImage Compression and Resizing Using Improved Seam Carving for Retinal Images
Image Compression and Resizing Using Improved Seam Carving for Retinal Images Prabhu Nayak 1, Rajendra Chincholi 2, Dr.Kalpana Vanjerkhede 3 1 PG Student, Department of Electronics and Instrumentation
More informationA New CGAN Technique for Constrained Topology Design Optimization. Abstract
A New CGAN Technique for Constrained Topology Design Optimization M.-H. Herman Shen 1 and Liang Chen Department of Mechanical and Aerospace Engineering The Ohio State University Abstract This paper presents
More informationarxiv: v2 [cs.cv] 25 Jul 2018
Unpaired Photo-to-Caricature Translation on Faces in the Wild Ziqiang Zheng a, Chao Wang a, Zhibin Yu a, Nan Wang a, Haiyong Zheng a,, Bing Zheng a arxiv:1711.10735v2 [cs.cv] 25 Jul 2018 a No. 238 Songling
More informationTowards Principled Methods for Training Generative Adversarial Networks. Martin Arjovsky & Léon Bottou
Towards Principled Methods for Training Generative Adversarial Networks Martin Arjovsky & Léon Bottou Unsupervised learning - We have samples from an unknown distribution Unsupervised learning - We have
More informationGenerative Adversarial Network
Generative Adversarial Network Many slides from NIPS 2014 Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio Generative adversarial
More informationIntroduction to Generative Adversarial Networks
Introduction to Generative Adversarial Networks Ian Goodfellow, OpenAI Research Scientist NIPS 2016 Workshop on Adversarial Training Barcelona, 2016-12-9 Adversarial Training A phrase whose usage is in
More informationOne Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models
One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models [Supplemental Materials] 1. Network Architecture b ref b ref +1 We now describe the architecture of the networks
More informationLecture 19: Generative Adversarial Networks
Lecture 19: Generative Adversarial Networks Roger Grosse 1 Introduction Generative modeling is a type of machine learning where the aim is to model the distribution that a given set of data (e.g. images,
More informationarxiv: v1 [cs.cv] 23 Nov 2017
Person Transfer GAN to Bridge Domain Gap for Person Re-Identification Longhui Wei 1, Shiliang Zhang 1, Wen Gao 1, Qi Tian 2 1 Peking University 2 University of Texas at San Antonio {longhuiwei, slzhang.jdl,
More informationGENERATIVE ADVERSARIAL NETWORKS (GAN) Presented by Omer Stein and Moran Rubin
GENERATIVE ADVERSARIAL NETWORKS (GAN) Presented by Omer Stein and Moran Rubin GENERATIVE MODEL Given a training dataset, x, try to estimate the distribution, Pdata(x) Explicitly or Implicitly (GAN) Explicitly
More informationarxiv: v1 [cs.cv] 1 Dec 2018
Internal Distribution Matching for Natural Image Retargeting Assaf Shocher Shai Bagon Phillip Isola Michal Irani Dept. of Computer Science and Applied Math, The Weizmann Institute of Science Computer Science
More informationStudy of Residual Networks for Image Recognition
Study of Residual Networks for Image Recognition Mohammad Sadegh Ebrahimi Stanford University sadegh@stanford.edu Hossein Karkeh Abadi Stanford University hosseink@stanford.edu Abstract Deep neural networks
More informationAdversarial Scene Editing: Automatic Object Removal from Weak Supervision
Adversarial Scene Editing: Automatic Object Removal from Weak Supervision Rakshith Shetty 1 Mario Fritz 2 Bernt Schiele 1 1 Max Planck Institute for Informatics, Saarland Informatics Campus 2 CISPA Helmholtz
More informationMulti-Content GAN for Few-Shot Font Style Transfer
Multi-Content GAN for Few-Shot Font Style Transfer Samaneh Azadi 1, Matthew Fisher 2, Vladimir Kim 2, Zhaowen Wang 2, Eli Shechtman 2, Trevor Darrell 1 1 UC Berkeley, 2 Adobe Research {sazadi,trevor}@eecs.berkeley.edu
More informationLearning to Discover Cross-Domain Relations with Generative Adversarial Networks
OUTPUT OUTPUT Learning to Discover Cross-Domain Relations with Generative Adversarial Networks Taeksoo Kim 1 Moonsu Cha 1 Hyunsoo Kim 1 Jung Kwon Lee 1 Jiwon Kim 1 Abstract While humans easily recognize
More informationUnsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks
Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks Minjun Li 1,2, Haozhi Huang 2, Lin Ma 2, Wei Liu 2, Tong Zhang 2, Yu-Gang Jiang 1 1 Shanghai Key Lab of Intelligent
More informationSelf-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material
Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material Ayush Tewari 1,2 Michael Zollhöfer 1,2,3 Pablo Garrido 1,2 Florian Bernard 1,2 Hyeongwoo
More informationarxiv: v1 [cs.cv] 17 Nov 2016
Inverting The Generator Of A Generative Adversarial Network arxiv:1611.05644v1 [cs.cv] 17 Nov 2016 Antonia Creswell BICV Group Bioengineering Imperial College London ac2211@ic.ac.uk Abstract Anil Anthony
More informationFACIAL POINT DETECTION BASED ON A CONVOLUTIONAL NEURAL NETWORK WITH OPTIMAL MINI-BATCH PROCEDURE. Chubu University 1200, Matsumoto-cho, Kasugai, AICHI
FACIAL POINT DETECTION BASED ON A CONVOLUTIONAL NEURAL NETWORK WITH OPTIMAL MINI-BATCH PROCEDURE Masatoshi Kimura Takayoshi Yamashita Yu Yamauchi Hironobu Fuyoshi* Chubu University 1200, Matsumoto-cho,
More informationSuper-Resolution on Image and Video
Super-Resolution on Image and Video Jason Liu Stanford University liujas00@stanford.edu Max Spero Stanford University maxspero@stanford.edu Allan Raventos Stanford University aravento@stanford.edu Abstract
More informationMulti-Content GAN for Few-Shot Font Style Transfer
Multi-Content GAN for Few-Shot Font Style Transfer Samaneh Azadi 1, Matthew Fisher 2, Vladimir Kim 2, Zhaowen Wang 2, Eli Shechtman 2, Trevor Darrell 1 1 UC Berkeley, 2 Adobe Research {sazadi,trevor}@eecs.berkeley.edu
More informationAdaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision
Adaptive Zoom Distance Measuring System of Camera Based on the Ranging of Binocular Vision Zhiyan Zhang 1, Wei Qian 1, Lei Pan 1 & Yanjun Li 1 1 University of Shanghai for Science and Technology, China
More informationarxiv: v2 [cs.cv] 6 Dec 2017
Arbitrary Facial Attribute Editing: Only Change What You Want arxiv:1711.10678v2 [cs.cv] 6 Dec 2017 Zhenliang He 1,2 Wangmeng Zuo 4 Meina Kan 1 Shiguang Shan 1,3 Xilin Chen 1 1 Key Lab of Intelligent Information
More informationFlexible Calibration of a Portable Structured Light System through Surface Plane
Vol. 34, No. 11 ACTA AUTOMATICA SINICA November, 2008 Flexible Calibration of a Portable Structured Light System through Surface Plane GAO Wei 1 WANG Liang 1 HU Zhan-Yi 1 Abstract For a portable structured
More informationNeural Face Editing with Intrinsic Image Disentangling SUPPLEMENTARY MATERIAL
Neural Face Editing with Intrinsic Image Disentangling SUPPLEMENTARY MATERIAL Zhixin Shu 1 Ersin Yumer 2 Sunil Hadap 2 Kalyan Sunkavalli 2 Eli Shechtman 2 Dimitris Samaras 1,3 1 Stony Brook University
More informationVideo Analysis for Browsing and Printing
Video Analysis for Browsing and Printing Qian Lin, Tong Zhang, Mei Chen, Yining Deng, Brian Atkins HP Laboratories HPL-2008-215 Keyword(s): video mining, video printing, user intent, video panorama, video
More informationarxiv: v1 [cs.cv] 19 Apr 2017
Generative Face Completion Yijun Li 1, Sifei Liu 1, Jimei Yang 2, and Ming-Hsuan Yang 1 1 University of California, Merced 2 Adobe Research {yli62,sliu32,mhyang}@ucmerced.edu jimyang@adobe.com arxiv:1704.05838v1
More information2D-to-3D Facial Expression Transfer
2D-to-3D Facial Expression Transfer Gemma Rotger, Felipe Lumbreras, Francesc Moreno-Noguer and Antonio Agudo Computer Vision Center and Dpt. Ciències de la Computació, Universitat Autònoma de Barcelona,
More information